Related papers: The Codec Language Model-based Zero-Shot Spontaneo…

In this technical report, we describe our submission for the WildSpoof Challenge TTS Track: Text-to-Speech with In-the-Wild Data. We introduce F5-TTS-DPS, a model built upon the F5-TTS architecture. Our approach integrates Exponential…

Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized…

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical…

Conversation summarization loses nuanced details: when asked about coding preferences after 40 turns, summarization recalls "use type hints" but drops the critical constraint "everywhere" (19.0% exact match vs. 93.0% for our approach). We…

Singing Voice Synthesis (SVS) aims to generate expressive vocal performances from structured musical inputs such as lyrics and pitch sequences. While recent progress in discrete codec-based speech synthesis has enabled zero-shot generation…

In zero-shot text-to-speech, achieving a balance between fidelity to the target speaker and adherence to text content remains a challenge. While classifier-free guidance (CFG) strategies have shown promising results in image generation,…

We present a novel way of conditioning a pretrained denoising diffusion speech model to produce speech in the voice of a novel person unseen during training. The method requires a short (~3 seconds) sample from the target person, and…

Open-Domain Question Answering (ODQA) aims to answer questions without explicitly providing specific background documents. This task becomes notably challenging in a zero-shot setting where no data is available to train tailored…

Dialogue State Tracking (DST) is crucial for understanding user needs and executing appropriate system actions in task-oriented dialogues. Majority of existing DST methods are designed to work within predefined ontologies and assume the…

We present OmniVoice, a massively multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive (NAR) architecture. Unlike conventional…

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

Large language models (LLMs) have revolutionized natural language processing (NLP) with impressive performance across various text-based tasks. However, the extension of text-dominant LLMs to with speech generation tasks remains…

Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-fidelity texts or images in various tasks. In contrast, the current speech generative models are still struggling regarding…

Zero-shot Text-to-Speech (TTS) has recently advanced significantly, enabling models to synthesize speech from text using short, limited-context prompts. These prompts serve as voice exemplars, allowing the model to mimic speaker identity,…

We present a speaker conditioned text-to-speech (TTS) system aimed at addressing challenges in generating speech for unseen speakers and supporting diverse Indian languages. Our method leverages a diffusion-based TTS architecture, where a…

Recently, the acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion was shown as a natural end-to-end model directly targeting words as output units. However, this type of word-based CTC model suffers…

With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling based decoding strategies bring…

Large language models (LLMs) are increasingly prevalent in conversational systems due to their advanced understanding and generative capabilities in general contexts. However, their effectiveness in task-oriented dialogues (TOD), which…

Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech tokens. We present LLaDA-TTS, which replaces the AR LLM with…

Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of…